检索结果-内蒙古大学图书馆

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Riccardo Franceschini Javier Rodriguez Marquez Matteo Fumagalli Julian Cayero Becerra Eurecat Centre Tecnològic de Catalunya Robotics and Automation Unit Cerdanyola del Vallès Barcelona Spain Department of Electrical Engineering Automation and Control Group Danish Technical University Lyngby Denmark

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Operating unmanned aerial vehicles (UAVs) for assets inspections poses distinct challenges encompassing the need to maintain a safe distance from the inspection area, ensure correct orientation towards the inspected surface, and achieve comprehensive coverage of the entire surface. Achieving these tasks is inherently complex and stressful. Therefore, a novel approach that seeks to enhance the piloting experience by harnessing the latest advancements in segmentation models, such as Segment Anything Model (SAM), is proposed. These models, thanks to their prompting capabilities, allow seamless communication between the operator and the UAV, opening up the possibility of defining intricate inspection regions through simple interactions. Within this approach, decision-making authority remains with the operator, while the UAV takes on the demanding task of segmenting the designated area and devising an appropriate traversal plan. Throughout this process, the operator’s situational awareness is heightened through visual cues overlaid on the camera stream and a 3D panel presenting information of the drone position and spatially sensed data. This teleoperation framework allows the operator to maintain continuous control of the ongoing operation through a simplified interface. The paper delineates both the system and the methodology employed, showcasing the effectiveness of integrating segmentation models into the decision-making workflow. The validity of the proposed framework is established through testing within a photorealistic UAV simulator along with real experiments in a controlled laboratory environment.

关键词： Visualization Three-dimensional displays Decision making Laboratories Inspection Traveling salesman problems Autonomous aerial vehicles Robot sensing systems Spatial databases Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Sosegformer: A Cross-Scale Feature Correlated Network For Small Medical Object Segmentation

Sosegformer: A Cross-Scale Feature Correlated Network For Sm...

引用

IEEE International Symposium on Biomedical Imaging

作者： Wei Dai Zixuan Wu Rui Liu Junxian Zhou Min Wang Tianyi Wu Jun Liu Centre for Robotics and Automation City University of Hong Kong Hong Kong China Department of Mechanical Engineering City University of Hong Kong Hong Kong China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

A mild syndrome with a small infected region is an ominous warning and is foremost in the early diagnosis of diseases. Recently, deep learning algorithms, such as convolutional neural networks (CNN), have been successfully applied to segment natural or medical objects, yielding promising results. However, the analysis of medical objects with small area occupation in images remains largely underexplored. This task poses a significant challenge due to information loss caused by convolution and pooling operations in CNN, particularly for small medical objects. To tackle these challenges, we propose a novel small-object segmentation with transformer (SoSegFormer) network for accurate small-object segmentation in medical images. Quantitative experimental results demonstrate the top-level performance of SoSegFormer, achieving the best mIoU, mDice, MAE, and F2 Score. Notably, it achieved 87.02%, 80.91%, and 65.17% in mDice for segmenting liver tumour, polyp, and sperm objects, which occupy less than 1% of the image areas in ATLAS, PolypGen, and SemSperm datasets.

关键词： Image segmentation Visualization Morphology Object segmentation Medical services Transformers Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Compact 3D Gaussian Splatting for Dense Visual SLAM

arXiv

引用

arXiv 2024年

作者： Deng, Tianchen Chen, Yaohui Zhang, Leyan Yang, Jianfei Yuan, Shenghai Liu, Jiuming Wang, Danwei Wang, Hesheng Chen, Weidong Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, when we revisit the existing GS-based SLAM systems, we observe that the redundancy of the Gaussian ellipsoids created by SLAM systems is significantly superior to those of the original 3D Gaussian Splatting methods. We further quantitatively demonstrate the geometric similarity and the redundancy of 3D Gaussian scene representation, leading to high memory and storage costs. To address this limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then, a novel geometry codebook-based quantization method is proposed to further compress 3D Gaussian geometric attributes. Robust and accurate pose estimation is achieved by a local-to-global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training, rendering speed (226% increase), and low memory usage (2.21× compression) while maintaining the state-of-the-art (SOTA) quality of the scene representation. https://***/dtc111111/CompactGSSLAM Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Definition for Detecting Abnormal Perspiration Patterns in High-Stress Professions 23

Digital Twin Definition for Detecting Abnormal Perspiration ...

引用

23rd RoEduNet Conference: Networking in Education and Research, RoEduNet 2024

作者： Vizitiu, Cristian Turcin, Ioan Dominey, Kevin Alexander Softic, Selver Dinculescu, Adrian-Catalin Bocanet, Vlad I. Dugan, Cosmin Moraru, Sorin-Aurel The Space Applications and Technologies Laboratory Institute of Space Science-Subsidiary of INFLPR Magurele Romania Transilvania University of Brasov Faculty of Electrical Engineering and Computer Science Department of Automatics and Information Technology Brasov Romania CAMPUS 02 University of Applied Sciences Department Automation Technology Graz Austria CAMPUS 02 University of Applied Sciences Department IT and Business Informatics Graz Austria Robotics and Production Management Technical University of Cluj-Napoca Cluj-Napoca Faculty of Industrial Engineering Department of Manufacturing Engineering Romania Bucharest University Emergency Hospital Bucharest Romania

ISBN: (纸本)9798331540388

Perspiration is a physiological response in high-stress situations, that also plays a key role in thermoregulation and stress management. Understanding perspiration patterns is used for assessing physiological responses and optimizing human performance especially in professions such as emergency medical services and military operations, as well as for individuals exposed to Isolated Confined Extreme (ICE) environments such as astronauts and space analog mission participants. This paper defines a Digital Twin (DT) model, that will be integrated with an existing physical sweat simulator module (SSM) prototype. Its goal is to simulate human perspiration under high-stress conditions by integrating environmental, physiological, and psychological data. The system architecture is developed via Model-Based Systems engineering (MBSE). The scope of the designed virtual model is to accurately reflect physical perspiration, detect abnormal perspiration patterns, and generate recommendations regarding stress countermeasures. The goal is to influence the behavioral and/or physiological state of the physical twin, thereby creating a dynamic, responsive system. Machine learning (ML) models will be used to identify patterns in the environmental, physiological, and psychological inputs and predict sweat volume, chemical composition, and regional sweat distributions across the body. ML will also be used to detect abnormal perspiration patterns based on input data. The application of generative AI for creating test data from simulation templates is anticipated to facilitate the comparative analysis of two to three distinct profiles, such as astronauts, soldiers, and paramedics or firefighters, using simulated values. The SSM, with its integrated sensors, will serve the dual purpose of validating the model and providing realistic physical simulation. © 2024 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Smart Shopping and Cart Billing System Using Deep Learning

Smart Shopping and Cart Billing System Using Deep Learning

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Ramkumar S Saravanan R Kanagaraj Venusamy Rani Jabbar N. Jeevitha Department of Robotics and Automation Rajalakshmi Engineering College Thandalam Chennai India Department of Mechatronics Engineering Rajalakshmi Engineering College Chennai India EDICT Department Electrical Engineering Program Bahrain polytechnic Isa town Kingdom of Bahrain Department of Electrical and Electronics Engineering Roever Engineering College Perambalur India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

There are many problems faced by people who stand for hours at billing counter after shopping, even though crowds are avoided everywhere, shopping mall billing queue isn't reducing since ages. Since the world relies on automation today, everyone has to automate processes which consumes time, money and efforts wherever possible. The technique related with the use of Raspberry Pi, LCD display and Webcam helps the people to bill the groceries within the shopping cart. It reduces consumption of time and their energy can be conserved which can't happen when they stand in a queue for billing process. User have to scan the object in front of webcam and LCD display allows them to add purchased items along with their price and quantity. They can also remove the product fromthe cart and it will be automatically removed. At the end of process, payment can be made online using a QR code or UPI. The Bill will be generated to their respective mail or it will be sent as SMS. User have to register or Log in when they start shopping. Automatic detection is possible without any inspection behind. The model is much portable and does not face any problem in its operation. When compared with the existing methods the processor, display along with its webcam accuracy is much better, it does not require complete continuous guidance and maintenance upon its usage. The need to push the cart has been eliminated as the cart can move along/follow the user autonomously.

关键词： Deep learning Webcams QR codes Inspection Liquid crystal displays Registers Maintenance Internet of Things Faces Postal services

来源：评论

学校读者我要写书评

暂无评论

SR-Mamba: Effective Surgical Phase Recognition with State Space Model

arXiv

引用

arXiv 2024年

作者： Cao, Rui Wang, Jiangliu Liu, Yun-Hui Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong

Surgical phase recognition is crucial for enhancing the efficiency and safety of computer-assisted interventions. One of the fundamental challenges involves modeling the long-distance temporal relationships present in surgical videos. Inspired by the recent success of Mamba, a state space model with linear scalability in sequence length, this paper presents SR-Mamba, a novel attention-free model specifically tailored to meet the challenges of surgical phase recognition. In SR-Mamba, we leverage a bidirectional Mamba decoder to effectively model the temporal context in overlong sequences. Moreover, the efficient optimization of the proposed Mamba decoder facilitates single-step neural network training, eliminating the need for separate training steps as in previous works. This single-step training approach not only simplifies the training process but also ensures higher accuracy, even with a lighter spatial feature extractor. Our SR-Mamba establishes a new benchmark in surgical video analysis by demonstrating state-of-the-art performance on the Cholec80 and CATARACTS Challenge datasets. The code is accessible at https://***/rcao-hk/SR-Mamba. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Neovascularization Detection in Color Fundus Photography Image 23

Deep Learning Based Neovascularization Detection in Color Fu...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Guo, Tianjiao Yang, Jie Yu, Qi Institute of Medical Robotics Institute of Image Processing and Pattern Recognition Department of Automation School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Shanghai General Hospital Shanghai Jiao Tong University School of Medicine Shanghai China National Clinical Research Center for Eye Diseases Shanghai China

ISBN: (纸本)9781450399029

Diabetic retinopathy (DR) has already been one of the leading causes of vision loss. A large number of researches about deep learning-based DR screening using color retinal photography images have been proposed in recent years. However, existing works mainly concentrated on non-proliferative diabetic retinopathy (NPDR) lesions. The exploration of proliferative diabetic retinopathy (PDR) lesion, which is more serious, is still insufficient. In this paper, we explored into one typical PDR lesion named neovascularization (NV). We collected and annotated retinal images from public and private datasets to construct and release a new dataset for NV detection. Three tasks including segmentation, detection, and grading were conducted on our dataset by using a set of state-of-the-art deep learning models. The results show that introducing NV detection can benefit DR grading. However, the segmentation and detection of NV are still challenging and have considerable room for improvement. © 2023 Copyright held by the owner/author(s).

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Neural Network Regression Analysis of Magnetic Sensor Data for Spatial Magnet Positioning

Neural Network Regression Analysis of Magnetic Sensor Data f...

引用

Electrical, Electronic and Computing engineering (IcETRAN), International Conference on

作者： Vladimir Sibinović Mirko Raković Department of Automatic Control Faculty of Electronic Engineering University of Niš Niš Serbia Chair of Mechatronics Robotics and Automation Faculty of Technical Science Novi Sad Serbia

ISBN: (数字)9798350386998

ISBN: (纸本)9798350387001

This paper deals with the magnet position estimation based on the measurements from multiple Hall sensors. Estimation of the position is obtained from trained artificial neural networks. Data are gathered using a custom sensor board that has eight three-axis Hall sensors on it, and correlation between magnetic field and position was determined to be able to estimate position in X and Y directions. First measurements were made to determine the optimal height of the magnet for later data gathering. The outcome of the research was evaluated by comparing the ground truth with the estimated values of the best-trained network to determine the error of estimation. Precise measurement of the position of the magnet is intended to be used for the development of a tactile sensor that estimates the contact force through the displacement of the magnet in the deformable layer.

关键词： Magnetic field measurement Systematics Magnetic sensors Layout Estimation Tactile sensors Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Health Data Analytics Using IoT: Transforming Healthcare Management and Treatment Strategies for Improved Patient Outcomes

Health Data Analytics Using IoT: Transforming Healthcare Man...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Tuan, Dinh Cong Unnikrishnan, Paravthy Dhandayuthapani, Bala Vennila, M.E.M. Long, Choi Sang Sahoo, Deepali Rani Dai Nam University Faculty of Communication Viet Nam Amritapuri690525 India College of Computing and Information Sciences University of Technology and Applied Sciences Department of It Shinas Campus Oman Karpaga Vinayaga College of Engineering and Technology Department of Robotics and Automation Chengalpattu India Raffles University Faculty of Business Malaysia Symbiosis Law School Noida India Pune India

ISBN: (纸本)9798331543617

The integration of Web of Things (IoT) innovation within the healthcare segment has revolutionized conventional healthcare administration and treatment procedures, driving progressed quiet results. This paper looks at the transformative effect of well-being information analytics utilizing IoT in upgrading healthcare administrations, optimizing understanding care, and advancing preventive measures. The paper analyzes the key components and applications of IoT in healthcare, emphasizing its part in information collection, real-time observation, and examination of understanding imperative signs, action levels, and pharmaceutical adherence. With the help of IoT-enabled gadgets such as wearables, sensors, and keen checking frameworks, healthcare experts can assemble comprehensive, real-time persistent information, encouraging early discovery and opportune mediation for basic well-being issues. Besides, the utilization of IoT in well-being information analytics empowers the improvement of personalized treatment plans custom-fitted to a person's persistent needs, cultivating a patient-centric approach to healthcare conveyance. By leveraging machine learning calculations and prescient analytics, healthcare suppliers can expect potential well-being complications, in this manner minimizing the chance of antagonistic occasions and clinic readmissions. In addition, the execution of IoT-based healthcare arrangements advances further understanding and observing, empowering healthcare suppliers to offer ceaseless, personalized care past conventional healthcare settings. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Adaptive speed control of ROVs with experimental results from an aquaculture net pen inspection operation

Adaptive speed control of ROVs with experimental results fro...

引用

Mediterranean Conference on Control and automation (MED)

作者： Sveinung Johan Ohrem Linn Danielsen Evjemo Bent Oddvar Arnesen Haugaløkken Herman Biørn Amundsen Eleni Kelasidi Department of Aquaculture SINTEF Ocean AS Aquaculture robotics and automation Trondheim Norway Department of Engineering Cybernetics Norwegian University of Science and Technology Trondheim Norway

Remotely operated vehicles (ROVs) are often used for inspection in aquaculture net pens which serves the important purpose of localizing holes in the net and reporting potential irregularities and damages. Manual control of the vehicle inside a net pen, while simultaneously inspecting the net structure, is difficult and puts a lot of stress on the vehicle operators. Adaptation of new solutions that enables autonomous traversal of net pens where the vehicle maintains a fixed distance, heading, and velocity relative to the net is considered essential. One of the main challenges of such autonomous solutions is a robust and tight control of the vehicle’s velocities. To target this challenge, this paper presents adaptive speed controllers for the surge and sway speeds of a remotely operated vehicle with unknown parameters and under the influence of unknown external disturbances. The stability properties of the controllers are proven through Lyapunov theory, and both simulations and field experiments demonstrate their ability to track the desired speeds through the use of a net following scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：